TrueForge open-source agent harness cuts costs by 30%-75% in testing

omarsar0 · x · 2026-08-20

TrueFoundry released TrueForge, an open-source (MIT) agent runtime harness designed to be vendor-neutral. It manages tool-calling loops, context, sub-agents, and sandboxed code execution across OpenAI, Anthropic, Google, and open-weight models like Kimi, GLM, and DeepSeek. In a 14-task enterprise benchmark, TrueForge driving Opus 4.8 matched Claude Managed Agents' accuracy at 30% lower cost (3.8M vs 10M tokens). Routing to GLM-5.2 maintained accuracy while cutting costs by 75% ($3 vs $12).

Related event: TrueFoundry Open-Sources TrueForge Agent Harness(4 posts)→

Original post →

More from coding & agent

coding & agent channel →